Update README.md

README.md

@@ -72,7 +72,7 @@ model = VisionEncoderDecoderModel.from_pretrained("laicsiifes/swin-gportuguese-2
 tokenizer = AutoTokenizer.from_pretrained("laicsiifes/swin-gportuguese-2")
 image_processor = AutoImageProcessor.from_pretrained("laicsiifes/swin-gportuguese-2")
 
-# perform inference on an image
+# preprocess an image
 url = "http://images.cocodataset.org/val2017/000000039769.jpg"
 image = Image.open(requests.get(url, stream=True).raw)
 pixel_values = image_processor(image, return_tensors="pt").pixel_values
@@ -80,9 +80,20 @@ pixel_values = image_processor(image, return_tensors="pt").pixel_values
 # generate caption
 generated_ids = model.generate(pixel_values)
 generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
-print(generated_text)
 ```
 
+```python
+import matplotlib.pyplot as plt
+
+# plot image with caption
+plt.imshow(image)
+plt.axis("off")
+plt.title(generated_text)
+plt.show()
+```
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/637a149c0dbdecf0b5bd6490/tl1YYtNIx4CCCKDPwKgk1.png)
+
 ## 📈 Results
 
 The evaluation metrics Cider-D, BLEU@4, ROUGE-L, METEOR and BERTScore